Simulation Data: Sentiment Analysis Text Framing News About Immigrants

Create Data;

1. Data Collection

• Data Sources: Collect news or articles related to immigrants from various media sources.

• Extracted Text: Extract text from the news, either in the form of full articles or certain paragraphs that focus on immigration issues.

  2. Text Pre-Processing

• Tokenization: Breaking text into words or phrases that can be analyzed.

• Normalization: Changing words to their basic form (lemmatization) and removing stop words (common words that are not important).

• Data Cleaning: Removing irrelevant punctuation, numbers, and symbols.

datawords <-data.frame(
  Words = c("Refugees","Discrimiation","Hates","Murder", "Steal","Kill",
             "Death","Racism","Dark","Black","Bad","Slaughterer","Human",
             "Right","Safety","Development", "Ecoonmic","Money","Transfer",
             "Population","Demogrphy","Show","Massacre","Rapits", "Gun",
             "Violance","Terror","Sexsuality","Anti","Uncertainty"),
  
  Sentiment = c("Negative","Negative", "Negative","Negative","Negative",
                "Negative","Negative","Negative","Negative", "Negative",
                "Negative","Negative","Positive","Positive","Positive",
                "Positive","Positive","Positive","Positive","Positive",
                "Positive","Positive","Negative","Negative","Negative",
                "Negative","Negative","Negative","Negative","Negative"),
  
  Data = c(5500,4500,4300,4021,3991,3812,3711,3300,3110,3000,2911,2912,
           4900,4211,3999,3555,3122,2821,2742,2641,2521,2240,2821,2712,
           2681,2531,2412,2341,2222,1999))

Create Visual Analysis;

library(tidytext)
library(ggplot2)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

datawords %>%
  group_by(Sentiment) %>%
  top_n(30) %>%
  ggplot(aes(reorder(Words, Data), Data, fill = Sentiment)) +
  geom_bar(alpha = 0.8, stat = "identity", show.legend = TRUE) +
  facet_wrap(~Sentiment, scales = "free_y") +
  labs(title = "Sentiment Analysis Text Framing News About Immigrants",
       y = "Text Amount", x = NULL) +
  coord_flip() +
  theme_bw()

## Selecting by Data

Read Data;

1. Sentiment Analysis

• Sentiment Labeling: Use Natural Language Processing (NLP) techniques to classify words or phrases into sentiment categories, such as positive, negative, or neutral.

• Sentiment Dictionary: Some words or phrases found in the text will be compared with an existing sentiment dictionary (lexicon) to assess whether the word has a positive or negative connotation.

2. Keyword Framing

• Word Frequency: Count the frequency of certain words or phrases that appear in the news, and group them based on sentiment (positive or negative).

• Sentiment Separation: The results of the sentiment analysis are separated into two groups: positive and negative, as seen in the image.

3. Data Visualization

• Bar Chart; The results of word frequency based on sentiment are then visualized in the form of a bar graph, which shows the number of occurrences of certain words.

• Sentiment Separation; The graph is separated into two parts: one for negative sentiment and one for positive sentiment, with the number of occurrences of words on the X-axis and the words on the Y-axis.

• Color: Different colors are used to differentiate sentiments (e.g. red for negative, blue for positive).

4. Interpretation

• Framing Analysis: By looking at the most frequently occurring words, you can see how the media frames news about immigrants, either positively or negatively.

• Conclusion:Based on this analysis, conclusions can be drawn about bias or tendencies in news reporting about immigrants.

• These are the general steps taken to produce a sentiment analysis and text framing as shown in the figure.